Skip to main content
Glama

device_command supervisor task

device_command_supervisor_task

Controls an incident recovery browser session with click, wait, save-and-close, and cancel commands; requires a write-scope key and verifies access via follow-up previews.

Instructions

Operate only this incident’s recovery browser. CLICK uses screenshot pixel coordinates; WAIT uses milliseconds. SAVE_AND_CLOSE persists browser state encrypted server-side. CANCEL ends the session. Never claim a challenge was solved until a subsequent preview verifies access. Requires a write-scope key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "jobId": "<jobId>",
      "leaseToken": "<leaseToken>",
      "command": "<command>"
    },
    "name": "device_command_supervisor_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYes
commandYes
leaseTokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and discloses important behavior: CLICK uses screenshot pixel coordinates, WAIT is in milliseconds, SAVE_AND_CLOSE persists encrypted browser state, CANCEL ends the session, and a write-scope key is required. It also adds a verification rule about not claiming success before a preview confirms access, though it does not cover error behavior or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded, with each sentence adding operational meaning about scope, command semantics, persistence, session termination, verification, and key requirements. It avoids repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter browser-command tool with no annotations and no output schema, the description provides substantial operational context, including command behavior and verification requirements. It is slightly incomplete because jobId and leaseToken are not explicitly described, but it is otherwise sufficient for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. It does well for the command union by clarifying CLICK coordinates, WAIT milliseconds, SAVE_AND_CLOSE persistence, and CANCEL behavior, but it leaves jobId and leaseToken only indirectly explained through references to the incident and write-scope key.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: operate the incident's recovery browser, with command types CLICK, WAIT, SAVE_AND_CLOSE, and CANCEL. It is clear what the tool does, though it does not explicitly contrast itself with sibling device tools such as the screenshot or preview tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a scope constraint, operating only this incident's recovery browser, and mentions using a subsequent preview to verify access. However, it does not explicitly say when to choose this tool over sibling device tools like device_screenshot_supervisor_task or preview_supervisor_task.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.